Mahsa Afsharizadeh

Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning

Ahmad Pouramini, Mahsa Afsharizadeh

This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary between a descriptive prefix (h…Read more